Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6422
    Prev
    Next
    INDEX
    Explanations

    miscellaneous terms and phrases such as "outtakes" and "out-of-court" related to various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "outs" or "outsourcing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.71
    antine
    -0.67
     Tata
    -0.66
    kefeller
    -0.65
    agall
    -0.65
    emporary
    -0.65
    iard
    -0.63
    unal
    -0.63
    atomic
    -0.63
    rette
    -0.62
    POSITIVE LOGITS
    dden
    0.80
    oeuv
    0.67
    wed
    0.66
    stretched
    0.64
     encour
    0.64
     flyers
    0.61
     impression
    0.59
    =\"
    0.59
    aught
    0.58
     shock
    0.58
    Activations Density 0.076%

    No Known Activations